1 Preparations

1.1 Settings

library(dplyr)
library(readr)
library(purrr)
library(knitr)

library(datamodelr)

options(scipen=10, readr.num_columns = 0)
opts_chunk$set(
  #out.width = '\\maxwidth'
  highlight = T
)

1.2 Data Prep

filenames <- c("Cities","Conferences","ConferenceTourneyGames","Events_2010","GameCities","MasseyOrdinals","NCAATourneyCompactResults", "NCAATourneyDetailedResults","NCAATourneySeedRoundSlots", "NCAATourneySeeds", "NCAATourneySlots", "Players_2010","RegularSeasonCompactResults","RegularSeasonDetailedResults","Seasons","SecondaryTourneyCompactResults","SecondaryTourneyTeams","TeamCoaches","TeamConferences","Teams","TeamSpellings")

data <- lapply(filenames, function(x){read_csv(paste0("/mnt/data/mens-machine-learning-competition-2019/",x,".csv"))})
names(data) <- filenames
dm_kaggle <- dm_from_data_frames(data)

1.3 Data Check

map(data, str)

## Classes 'spec_tbl_df', 'tbl_df', 'tbl' and 'data.frame': 421 obs. of  3 variables:
##  $ CityID: num  4001 4002 4003 4004 4005 ...
##  $ City  : chr  "Abilene" "Akron" "Albany" "Albuquerque" ...
##  $ State : chr  "TX" "OH" "NY" "NM" ...
##  - attr(*, "spec")=
##   .. cols(
##   ..   CityID = col_double(),
##   ..   City = col_character(),
##   ..   State = col_character()
##   .. )
## Classes 'spec_tbl_df', 'tbl_df', 'tbl' and 'data.frame': 51 obs. of  2 variables:
##  $ ConfAbbrev : chr  "a_sun" "a_ten" "aac" "acc" ...
##  $ Description: chr  "Atlantic Sun Conference" "Atlantic 10 Conference" "American Athletic Conference" "Atlantic Coast Conference" ...
##  - attr(*, "spec")=
##   .. cols(
##   ..   ConfAbbrev = col_character(),
##   ..   Description = col_character()
##   .. )
## Classes 'spec_tbl_df', 'tbl_df', 'tbl' and 'data.frame': 4861 obs. of  5 variables:
##  $ Season    : num  2001 2001 2001 2001 2001 ...
##  $ ConfAbbrev: chr  "a_sun" "a_sun" "a_sun" "a_sun" ...
##  $ DayNum    : num  121 121 122 122 122 122 123 123 124 128 ...
##  $ WTeamID   : num  1194 1416 1209 1359 1391 ...
##  $ LTeamID   : num  1144 1240 1194 1239 1273 ...
##  - attr(*, "spec")=
##   .. cols(
##   ..   Season = col_double(),
##   ..   ConfAbbrev = col_character(),
##   ..   DayNum = col_double(),
##   ..   WTeamID = col_double(),
##   ..   LTeamID = col_double()
##   .. )
## Classes 'spec_tbl_df', 'tbl_df', 'tbl' and 'data.frame': 2502630 obs. of  11 variables:
##  $ EventID       : num  1 2 3 4 5 6 7 8 9 10 ...
##  $ Season        : num  2010 2010 2010 2010 2010 2010 2010 2010 2010 2010 ...
##  $ DayNum        : num  7 7 7 7 7 7 7 7 7 7 ...
##  $ WTeamID       : num  1143 1143 1143 1143 1143 ...
##  $ LTeamID       : num  1293 1293 1293 1293 1293 ...
##  $ WPoints       : num  0 0 0 0 0 2 0 0 2 0 ...
##  $ LPoints       : num  0 0 0 0 0 0 0 0 2 0 ...
##  $ ElapsedSeconds: num  0 0 0 10 10 14 36 36 40 56 ...
##  $ EventTeamID   : num  1143 1143 1143 1143 1143 ...
##  $ EventPlayerID : num  600578 600584 600585 600581 600581 ...
##  $ EventType     : chr  "sub_in" "sub_in" "sub_in" "miss2_lay" ...
##  - attr(*, "spec")=
##   .. cols(
##   ..   EventID = col_double(),
##   ..   Season = col_double(),
##   ..   DayNum = col_double(),
##   ..   WTeamID = col_double(),
##   ..   LTeamID = col_double(),
##   ..   WPoints = col_double(),
##   ..   LPoints = col_double(),
##   ..   ElapsedSeconds = col_double(),
##   ..   EventTeamID = col_double(),
##   ..   EventPlayerID = col_double(),
##   ..   EventType = col_character()
##   .. )
## Classes 'spec_tbl_df', 'tbl_df', 'tbl' and 'data.frame': 49235 obs. of  6 variables:
##  $ Season : num  2010 2010 2010 2010 2010 2010 2010 2010 2010 2010 ...
##  $ DayNum : num  7 7 7 7 9 9 9 10 10 11 ...
##  $ WTeamID: num  1143 1314 1326 1393 1143 ...
##  $ LTeamID: num  1293 1198 1108 1107 1178 ...
##  $ CRType : chr  "Regular" "Regular" "Regular" "Regular" ...
##  $ CityID : num  4027 4061 4080 4340 4027 ...
##  - attr(*, "spec")=
##   .. cols(
##   ..   Season = col_double(),
##   ..   DayNum = col_double(),
##   ..   WTeamID = col_double(),
##   ..   LTeamID = col_double(),
##   ..   CRType = col_character(),
##   ..   CityID = col_double()
##   .. )
## Classes 'spec_tbl_df', 'tbl_df', 'tbl' and 'data.frame': 3492320 obs. of  5 variables:
##  $ Season       : num  2003 2003 2003 2003 2003 ...
##  $ RankingDayNum: num  35 35 35 35 35 35 35 35 35 35 ...
##  $ SystemName   : chr  "SEL" "SEL" "SEL" "SEL" ...
##  $ TeamID       : num  1102 1103 1104 1105 1106 ...
##  $ OrdinalRank  : num  159 229 12 314 260 249 228 204 183 26 ...
##  - attr(*, "spec")=
##   .. cols(
##   ..   Season = col_double(),
##   ..   RankingDayNum = col_double(),
##   ..   SystemName = col_character(),
##   ..   TeamID = col_double(),
##   ..   OrdinalRank = col_double()
##   .. )
## Classes 'spec_tbl_df', 'tbl_df', 'tbl' and 'data.frame': 2184 obs. of  8 variables:
##  $ Season : num  1985 1985 1985 1985 1985 ...
##  $ DayNum : num  136 136 136 136 136 136 136 136 136 136 ...
##  $ WTeamID: num  1116 1120 1207 1229 1242 ...
##  $ WScore : num  63 59 68 58 49 66 78 59 76 79 ...
##  $ LTeamID: num  1234 1345 1250 1425 1325 ...
##  $ LScore : num  54 58 43 55 38 58 54 58 57 70 ...
##  $ WLoc   : chr  "N" "N" "N" "N" ...
##  $ NumOT  : num  0 0 0 0 0 0 0 0 0 0 ...
##  - attr(*, "spec")=
##   .. cols(
##   ..   Season = col_double(),
##   ..   DayNum = col_double(),
##   ..   WTeamID = col_double(),
##   ..   WScore = col_double(),
##   ..   LTeamID = col_double(),
##   ..   LScore = col_double(),
##   ..   WLoc = col_character(),
##   ..   NumOT = col_double()
##   .. )
## Classes 'spec_tbl_df', 'tbl_df', 'tbl' and 'data.frame': 1048 obs. of  34 variables:
##  $ Season : num  2003 2003 2003 2003 2003 ...
##  $ DayNum : num  134 136 136 136 136 136 136 136 136 136 ...
##  $ WTeamID: num  1421 1112 1113 1141 1143 ...
##  $ WScore : num  92 80 84 79 76 58 67 74 65 64 ...
##  $ LTeamID: num  1411 1436 1272 1166 1301 ...
##  $ LScore : num  84 51 71 73 74 53 57 69 60 61 ...
##  $ WLoc   : chr  "N" "N" "N" "N" ...
##  $ NumOT  : num  1 0 0 0 1 0 0 0 0 0 ...
##  $ WFGM   : num  32 31 31 29 27 17 19 20 24 28 ...
##  $ WFGA   : num  69 66 59 53 64 52 54 47 56 51 ...
##  $ WFGM3  : num  11 7 6 3 7 4 4 6 5 2 ...
##  $ WFGA3  : num  29 23 14 7 20 14 13 14 14 6 ...
##  $ WFTM   : num  17 11 16 18 15 20 25 28 12 6 ...
##  $ WFTA   : num  26 14 22 25 23 27 31 37 14 11 ...
##  $ WOR    : num  14 11 10 11 18 12 13 8 15 7 ...
##  $ WDR    : num  30 36 27 20 20 29 27 28 23 20 ...
##  $ WAst   : num  17 22 18 15 17 8 4 12 15 13 ...
##  $ WTO    : num  12 16 9 18 13 14 16 12 14 11 ...
##  $ WStl   : num  5 10 7 13 8 3 10 2 11 8 ...
##  $ WBlk   : num  3 7 4 1 2 8 8 2 4 4 ...
##  $ WPF    : num  22 8 19 19 14 16 23 15 14 17 ...
##  $ LFGM   : num  29 20 25 27 25 20 18 26 22 23 ...
##  $ LFGA   : num  67 64 69 60 56 64 54 66 58 56 ...
##  $ LFGM3  : num  12 4 7 7 9 2 3 10 8 6 ...
##  $ LFGA3  : num  31 16 28 17 21 17 11 27 24 17 ...
##  $ LFTM   : num  14 7 14 12 15 11 18 7 8 9 ...
##  $ LFTA   : num  31 7 21 17 20 13 22 10 13 10 ...
##  $ LOR    : num  17 8 20 14 10 15 11 13 17 13 ...
##  $ LDR    : num  28 26 22 17 26 26 24 22 18 19 ...
##  $ LAst   : num  16 12 11 20 16 11 8 13 10 13 ...
##  $ LTO    : num  15 17 12 21 14 11 19 10 14 13 ...
##  $ LStl   : num  5 10 2 6 5 8 5 7 6 6 ...
##  $ LBlk   : num  0 3 5 6 8 4 4 6 5 1 ...
##  $ LPF    : num  22 15 18 21 19 22 19 24 16 15 ...
##  - attr(*, "spec")=
##   .. cols(
##   ..   Season = col_double(),
##   ..   DayNum = col_double(),
##   ..   WTeamID = col_double(),
##   ..   WScore = col_double(),
##   ..   LTeamID = col_double(),
##   ..   LScore = col_double(),
##   ..   WLoc = col_character(),
##   ..   NumOT = col_double(),
##   ..   WFGM = col_double(),
##   ..   WFGA = col_double(),
##   ..   WFGM3 = col_double(),
##   ..   WFGA3 = col_double(),
##   ..   WFTM = col_double(),
##   ..   WFTA = col_double(),
##   ..   WOR = col_double(),
##   ..   WDR = col_double(),
##   ..   WAst = col_double(),
##   ..   WTO = col_double(),
##   ..   WStl = col_double(),
##   ..   WBlk = col_double(),
##   ..   WPF = col_double(),
##   ..   LFGM = col_double(),
##   ..   LFGA = col_double(),
##   ..   LFGM3 = col_double(),
##   ..   LFGA3 = col_double(),
##   ..   LFTM = col_double(),
##   ..   LFTA = col_double(),
##   ..   LOR = col_double(),
##   ..   LDR = col_double(),
##   ..   LAst = col_double(),
##   ..   LTO = col_double(),
##   ..   LStl = col_double(),
##   ..   LBlk = col_double(),
##   ..   LPF = col_double()
##   .. )
## Classes 'spec_tbl_df', 'tbl_df', 'tbl' and 'data.frame': 720 obs. of  5 variables:
##  $ Seed       : chr  "W01" "W01" "W01" "W01" ...
##  $ GameRound  : num  1 2 3 4 5 6 1 2 3 4 ...
##  $ GameSlot   : chr  "R1W1" "R2W1" "R3W1" "R4W1" ...
##  $ EarlyDayNum: num  136 138 143 145 152 154 136 138 143 145 ...
##  $ LateDayNum : num  137 139 144 146 152 154 137 139 144 146 ...
##  - attr(*, "spec")=
##   .. cols(
##   ..   Seed = col_character(),
##   ..   GameRound = col_double(),
##   ..   GameSlot = col_character(),
##   ..   EarlyDayNum = col_double(),
##   ..   LateDayNum = col_double()
##   .. )
## Classes 'spec_tbl_df', 'tbl_df', 'tbl' and 'data.frame': 2218 obs. of  3 variables:
##  $ Season: num  1985 1985 1985 1985 1985 ...
##  $ Seed  : chr  "W01" "W02" "W03" "W04" ...
##  $ TeamID: num  1207 1210 1228 1260 1374 ...
##  - attr(*, "spec")=
##   .. cols(
##   ..   Season = col_double(),
##   ..   Seed = col_character(),
##   ..   TeamID = col_double()
##   .. )
## Classes 'spec_tbl_df', 'tbl_df', 'tbl' and 'data.frame': 2184 obs. of  4 variables:
##  $ Season    : num  1985 1985 1985 1985 1985 ...
##  $ Slot      : chr  "R1W1" "R1W2" "R1W3" "R1W4" ...
##  $ StrongSeed: chr  "W01" "W02" "W03" "W04" ...
##  $ WeakSeed  : chr  "W16" "W15" "W14" "W13" ...
##  - attr(*, "spec")=
##   .. cols(
##   ..   Season = col_double(),
##   ..   Slot = col_character(),
##   ..   StrongSeed = col_character(),
##   ..   WeakSeed = col_character()
##   .. )
## Classes 'spec_tbl_df', 'tbl_df', 'tbl' and 'data.frame': 5287 obs. of  4 variables:
##  $ PlayerID  : num  600001 600002 600003 600004 600005 ...
##  $ Season    : num  2010 2010 2010 2010 2010 2010 2010 2010 2010 2010 ...
##  $ TeamID    : num  1102 1102 1102 1102 1102 ...
##  $ PlayerName: chr  "BOHANNON_ZACH" "BRAKEVILLE_ADAM" "BROEKHUIS_TAYLOR" "BROOKS_DEREK" ...
##  - attr(*, "spec")=
##   .. cols(
##   ..   PlayerID = col_double(),
##   ..   Season = col_double(),
##   ..   TeamID = col_double(),
##   ..   PlayerName = col_character()
##   .. )
## Classes 'spec_tbl_df', 'tbl_df', 'tbl' and 'data.frame': 156089 obs. of  8 variables:
##  $ Season : num  1985 1985 1985 1985 1985 ...
##  $ DayNum : num  20 25 25 25 25 25 25 25 25 25 ...
##  $ WTeamID: num  1228 1106 1112 1165 1192 ...
##  $ WScore : num  81 77 63 70 86 79 64 58 98 97 ...
##  $ LTeamID: num  1328 1354 1223 1432 1447 ...
##  $ LScore : num  64 70 56 54 74 78 44 56 80 89 ...
##  $ WLoc   : chr  "N" "H" "H" "H" ...
##  $ NumOT  : num  0 0 0 0 0 0 0 0 0 0 ...
##  - attr(*, "spec")=
##   .. cols(
##   ..   Season = col_double(),
##   ..   DayNum = col_double(),
##   ..   WTeamID = col_double(),
##   ..   WScore = col_double(),
##   ..   LTeamID = col_double(),
##   ..   LScore = col_double(),
##   ..   WLoc = col_character(),
##   ..   NumOT = col_double()
##   .. )
## Classes 'spec_tbl_df', 'tbl_df', 'tbl' and 'data.frame': 82041 obs. of  34 variables:
##  $ Season : num  2003 2003 2003 2003 2003 ...
##  $ DayNum : num  10 10 11 11 11 11 12 12 12 12 ...
##  $ WTeamID: num  1104 1272 1266 1296 1400 ...
##  $ WScore : num  68 70 73 56 77 81 80 75 71 84 ...
##  $ LTeamID: num  1328 1393 1437 1457 1208 ...
##  $ LScore : num  62 63 61 50 71 55 62 61 66 56 ...
##  $ WLoc   : chr  "N" "N" "N" "N" ...
##  $ NumOT  : num  0 0 0 0 0 0 0 0 0 0 ...
##  $ WFGM   : num  27 26 24 18 30 26 23 28 28 32 ...
##  $ WFGA   : num  58 62 58 38 61 57 55 62 58 67 ...
##  $ WFGM3  : num  3 8 8 3 6 6 2 4 5 5 ...
##  $ WFGA3  : num  14 20 18 9 14 12 8 14 11 17 ...
##  $ WFTM   : num  11 10 17 17 11 23 32 15 10 15 ...
##  $ WFTA   : num  18 19 29 31 13 27 39 21 18 19 ...
##  $ WOR    : num  14 15 17 6 17 12 13 13 9 14 ...
##  $ WDR    : num  24 28 26 19 22 24 18 35 22 22 ...
##  $ WAst   : num  13 16 15 11 12 12 14 19 9 11 ...
##  $ WTO    : num  23 13 10 12 14 9 17 19 17 6 ...
##  $ WStl   : num  7 4 5 14 4 9 11 7 9 12 ...
##  $ WBlk   : num  1 4 2 2 4 3 1 2 2 0 ...
##  $ WPF    : num  22 18 25 18 20 18 25 21 23 13 ...
##  $ LFGM   : num  22 24 22 18 24 20 19 20 24 23 ...
##  $ LFGA   : num  53 67 73 49 62 46 41 59 52 52 ...
##  $ LFGM3  : num  2 6 3 6 6 3 4 4 6 3 ...
##  $ LFGA3  : num  10 24 26 22 16 11 15 17 18 14 ...
##  $ LFTM   : num  16 9 14 8 17 12 20 17 12 7 ...
##  $ LFTA   : num  22 20 23 15 27 17 28 23 27 12 ...
##  $ LOR    : num  10 20 31 17 21 6 9 8 13 9 ...
##  $ LDR    : num  22 25 22 20 15 22 21 25 26 23 ...
##  $ LAst   : num  8 7 9 9 12 8 11 10 13 10 ...
##  $ LTO    : num  18 12 12 19 10 19 30 15 25 18 ...
##  $ LStl   : num  9 8 2 4 7 4 10 14 8 1 ...
##  $ LBlk   : num  2 6 5 3 1 3 4 8 2 3 ...
##  $ LPF    : num  20 16 23 23 14 25 28 18 18 18 ...
##  - attr(*, "spec")=
##   .. cols(
##   ..   Season = col_double(),
##   ..   DayNum = col_double(),
##   ..   WTeamID = col_double(),
##   ..   WScore = col_double(),
##   ..   LTeamID = col_double(),
##   ..   LScore = col_double(),
##   ..   WLoc = col_character(),
##   ..   NumOT = col_double(),
##   ..   WFGM = col_double(),
##   ..   WFGA = col_double(),
##   ..   WFGM3 = col_double(),
##   ..   WFGA3 = col_double(),
##   ..   WFTM = col_double(),
##   ..   WFTA = col_double(),
##   ..   WOR = col_double(),
##   ..   WDR = col_double(),
##   ..   WAst = col_double(),
##   ..   WTO = col_double(),
##   ..   WStl = col_double(),
##   ..   WBlk = col_double(),
##   ..   WPF = col_double(),
##   ..   LFGM = col_double(),
##   ..   LFGA = col_double(),
##   ..   LFGM3 = col_double(),
##   ..   LFGA3 = col_double(),
##   ..   LFTM = col_double(),
##   ..   LFTA = col_double(),
##   ..   LOR = col_double(),
##   ..   LDR = col_double(),
##   ..   LAst = col_double(),
##   ..   LTO = col_double(),
##   ..   LStl = col_double(),
##   ..   LBlk = col_double(),
##   ..   LPF = col_double()
##   .. )
## Classes 'spec_tbl_df', 'tbl_df', 'tbl' and 'data.frame': 35 obs. of  6 variables:
##  $ Season : num  1985 1986 1987 1988 1989 ...
##  $ DayZero: chr  "10/29/1984" "10/28/1985" "10/27/1986" "11/2/1987" ...
##  $ RegionW: chr  "East" "East" "East" "East" ...
##  $ RegionX: chr  "West" "Midwest" "Southeast" "Midwest" ...
##  $ RegionY: chr  "Midwest" "Southeast" "Midwest" "Southeast" ...
##  $ RegionZ: chr  "Southeast" "West" "West" "West" ...
##  - attr(*, "spec")=
##   .. cols(
##   ..   Season = col_double(),
##   ..   DayZero = col_character(),
##   ..   RegionW = col_character(),
##   ..   RegionX = col_character(),
##   ..   RegionY = col_character(),
##   ..   RegionZ = col_character()
##   .. )
## Classes 'spec_tbl_df', 'tbl_df', 'tbl' and 'data.frame': 1551 obs. of  9 variables:
##  $ Season          : num  1985 1985 1985 1985 1985 ...
##  $ DayNum          : num  136 136 136 136 136 136 136 136 136 136 ...
##  $ WTeamID         : num  1151 1153 1201 1231 1249 ...
##  $ WScore          : num  67 77 79 79 78 77 77 79 80 59 ...
##  $ LTeamID         : num  1155 1245 1365 1139 1222 ...
##  $ LScore          : num  65 61 76 57 71 75 64 66 67 57 ...
##  $ WLoc            : chr  "H" "H" "H" "H" ...
##  $ NumOT           : num  0 0 0 0 0 0 0 0 0 0 ...
##  $ SecondaryTourney: chr  "NIT" "NIT" "NIT" "NIT" ...
##  - attr(*, "spec")=
##   .. cols(
##   ..   Season = col_double(),
##   ..   DayNum = col_double(),
##   ..   WTeamID = col_double(),
##   ..   WScore = col_double(),
##   ..   LTeamID = col_double(),
##   ..   LScore = col_double(),
##   ..   WLoc = col_character(),
##   ..   NumOT = col_double(),
##   ..   SecondaryTourney = col_character()
##   .. )
## Classes 'spec_tbl_df', 'tbl_df', 'tbl' and 'data.frame': 1568 obs. of  3 variables:
##  $ Season          : num  1985 1985 1985 1985 1985 ...
##  $ SecondaryTourney: chr  "NIT" "NIT" "NIT" "NIT" ...
##  $ TeamID          : num  1108 1133 1139 1145 1151 ...
##  - attr(*, "spec")=
##   .. cols(
##   ..   Season = col_double(),
##   ..   SecondaryTourney = col_character(),
##   ..   TeamID = col_double()
##   .. )
## Classes 'spec_tbl_df', 'tbl_df', 'tbl' and 'data.frame': 10994 obs. of  5 variables:
##  $ Season     : num  1985 1985 1985 1985 1985 ...
##  $ TeamID     : num  1102 1103 1104 1106 1108 ...
##  $ FirstDayNum: num  0 0 0 0 0 0 0 0 0 0 ...
##  $ LastDayNum : num  154 154 154 154 154 154 154 154 154 154 ...
##  $ CoachName  : chr  "reggie_minton" "bob_huggins" "wimp_sanderson" "james_oliver" ...
##  - attr(*, "spec")=
##   .. cols(
##   ..   Season = col_double(),
##   ..   TeamID = col_double(),
##   ..   FirstDayNum = col_double(),
##   ..   LastDayNum = col_double(),
##   ..   CoachName = col_character()
##   .. )
## Classes 'spec_tbl_df', 'tbl_df', 'tbl' and 'data.frame': 11241 obs. of  3 variables:
##  $ Season    : num  1985 1985 1985 1985 1985 ...
##  $ TeamID    : num  1114 1147 1204 1209 1215 ...
##  $ ConfAbbrev: chr  "a_sun" "a_sun" "a_sun" "a_sun" ...
##  - attr(*, "spec")=
##   .. cols(
##   ..   Season = col_double(),
##   ..   TeamID = col_double(),
##   ..   ConfAbbrev = col_character()
##   .. )
## Classes 'spec_tbl_df', 'tbl_df', 'tbl' and 'data.frame': 366 obs. of  4 variables:
##  $ TeamID       : num  1101 1102 1103 1104 1105 ...
##  $ TeamName     : chr  "Abilene Chr" "Air Force" "Akron" "Alabama" ...
##  $ FirstD1Season: num  2014 1985 1985 1985 2000 ...
##  $ LastD1Season : num  2019 2019 2019 2019 2019 ...
##  - attr(*, "spec")=
##   .. cols(
##   ..   TeamID = col_double(),
##   ..   TeamName = col_character(),
##   ..   FirstD1Season = col_double(),
##   ..   LastD1Season = col_double()
##   .. )
## Classes 'spec_tbl_df', 'tbl_df', 'tbl' and 'data.frame': 1141 obs. of  2 variables:
##  $ TeamNameSpelling: chr  "a&m-corpus chris" "a&m-corpus christi" "abilene chr" "abilene christian" ...
##  $ TeamID          : num  1394 1394 1101 1101 1101 ...
##  - attr(*, "spec")=
##   .. cols(
##   ..   TeamNameSpelling = col_character(),
##   ..   TeamID = col_double()
##   .. )

## $Cities
## NULL
## 
## $Conferences
## NULL
## 
## $ConferenceTourneyGames
## NULL
## 
## $Events_2010
## NULL
## 
## $GameCities
## NULL
## 
## $MasseyOrdinals
## NULL
## 
## $NCAATourneyCompactResults
## NULL
## 
## $NCAATourneyDetailedResults
## NULL
## 
## $NCAATourneySeedRoundSlots
## NULL
## 
## $NCAATourneySeeds
## NULL
## 
## $NCAATourneySlots
## NULL
## 
## $Players_2010
## NULL
## 
## $RegularSeasonCompactResults
## NULL
## 
## $RegularSeasonDetailedResults
## NULL
## 
## $Seasons
## NULL
## 
## $SecondaryTourneyCompactResults
## NULL
## 
## $SecondaryTourneyTeams
## NULL
## 
## $TeamCoaches
## NULL
## 
## $TeamConferences
## NULL
## 
## $Teams
## NULL
## 
## $TeamSpellings
## NULL

2 Schema Card with primary keys

I’m confused… I have no confidence.

dm_kaggle_primary_keys<- dm_add_references(
  dm_kaggle,
  ConferenceTourneyGames$Season == Seasons$Season,
  ConferenceTourneyGames$ConfAbbrev == Conferences$ConfAbbrev,
  Events_2010$Season == Seasons$Season,
  GameCities$CityID == Cities$CityID,
  GameCities$Season == Seasons$Season,
  NCAATourneyCompactResults$Season == Seasons$Season,
  NCAATourneyDetailedResults$Season == Seasons$Season,
  NCAATourneySeedRoundSlots$Seed == NCAATourneySeeds$Seed,
  NCAATourneySeeds$Season == Seasons$Season,
  NCAATourneySeeds$TeamID == Teams$TeamID,
  NCAATourneySlots$Season == Seasons$Season,
  Players_2010$Season == Seasons$Season,
  Players_2010$TeamID == Teams$TeamID,
  RegularSeasonCompactResults$Season == Seasons$Season,
  RegularSeasonDetailedResults$Season == Seasons$Season,
  SecondaryTourneyCompactResults$Season == Seasons$Season,
  MasseyOrdinals$TeamID == Teams$TeamID,
  MasseyOrdinals$Season == Seasons$Season,
  SecondaryTourneyTeams$Season == Seasons$Season,
  SecondaryTourneyTeams$TeamID == Teams$TeamID,
  TeamConferences$ConfAbbrev == Conferences$ConfAbbrev,
  TeamConferences$TeamID == Teams$TeamID,
  TeamConferences$Season == Seasons$Season,
  TeamCoaches$Season == Seasons$Season,
  TeamCoaches$TeamID == Teams$TeamID,
  TeamSpellings$TeamID == Teams$TeamID
)
graph <- dm_create_graph(dm_kaggle_primary_keys, rankdir = "BT", col_attr = c("column", "type"), edge_attrs = "dir = both, arrowtail = crow, arrowhead = odiamond", columnArrows = F)
dm_render_graph(graph)

3 Show Data

out <- NULL
for(i in 1:length(data)) {
  tab_name <- names(data[i])
  message <- paste0("ncol: ", ncol(data[[i]]))

  tab_section <- paste0(
    "\n## ", tab_name, "\n",
    message,"\n",
    "\n\n```{r}\n",
    "knitr::kable(data[[",i,"]] %>% head(10))\n",
    "\n\n```\n\n"
  )

  out <- c(out, knit_expand(text = tab_section))
}

3.1 Cities

ncol: 3

knitr::kable(data[[1]] %>% head(10))

CityID	City	State
4001	Abilene	TX
4002	Akron	OH
4003	Albany	NY
4004	Albuquerque	NM
4005	Allentown	PA
4006	Ames	IA
4007	Amherst	MA
4008	Anaheim	CA
4009	Anchorage	AK
4010	Ann Arbor	MI

3.2 Conferences

ncol: 2

knitr::kable(data[[2]] %>% head(10))

ConfAbbrev	Description
a_sun	Atlantic Sun Conference
a_ten	Atlantic 10 Conference
aac	American Athletic Conference
acc	Atlantic Coast Conference
aec	America East Conference
asc	American South Conference
awc	American West Conference
big_east	Big East Conference
big_eight	Big Eight Conference
big_sky	Big Sky Conference

3.3 ConferenceTourneyGames

ncol: 5

knitr::kable(data[[3]] %>% head(10))

Season	ConfAbbrev	DayNum	WTeamID	LTeamID
2001	a_sun	121	1194	1144
2001	a_sun	121	1416	1240
2001	a_sun	122	1209	1194
2001	a_sun	122	1359	1239
2001	a_sun	122	1391	1273
2001	a_sun	122	1407	1416
2001	a_sun	123	1209	1359
2001	a_sun	123	1407	1391
2001	a_sun	124	1209	1407
2001	a_ten	128	1173	1348

3.4 Events_2010

ncol: 11

knitr::kable(data[[4]] %>% head(10))

EventID	Season	DayNum	WTeamID	LTeamID	WPoints	LPoints	ElapsedSeconds	EventTeamID	EventPlayerID	EventType
1	2010	7	1143	1293	0	0	0	1143	600578	sub_in
2	2010	7	1143	1293	0	0	0	1143	600584	sub_in
3	2010	7	1143	1293	0	0	0	1143	600585	sub_in
4	2010	7	1143	1293	0	0	10	1143	600581	miss2_lay
5	2010	7	1143	1293	0	0	10	1143	600581	reb_off
6	2010	7	1143	1293	2	0	14	1143	600581	made2_jump
7	2010	7	1143	1293	0	0	36	1293	602791	miss2_jump
8	2010	7	1143	1293	0	0	36	1293	602781	reb_off
9	2010	7	1143	1293	2	2	40	1293	602781	made2_jump
10	2010	7	1143	1293	0	0	56	1143	600577	assist

3.5 GameCities

ncol: 6

knitr::kable(data[[5]] %>% head(10))

Season	DayNum	WTeamID	LTeamID	CRType	CityID
2010	7	1143	1293	Regular	4027
2010	7	1314	1198	Regular	4061
2010	7	1326	1108	Regular	4080
2010	7	1393	1107	Regular	4340
2010	9	1143	1178	Regular	4027
2010	9	1314	1300	Regular	4061
2010	9	1393	1352	Regular	4340
2010	10	1301	1209	Regular	4287
2010	10	1326	1241	Regular	4080
2010	11	1111	1423	Regular	4036

3.6 MasseyOrdinals

ncol: 5

knitr::kable(data[[6]] %>% head(10))

Season	RankingDayNum	SystemName	TeamID	OrdinalRank
2003	35	SEL	1102	159
2003	35	SEL	1103	229
2003	35	SEL	1104	12
2003	35	SEL	1105	314
2003	35	SEL	1106	260
2003	35	SEL	1107	249
2003	35	SEL	1108	228
2003	35	SEL	1110	204
2003	35	SEL	1111	183
2003	35	SEL	1112	26

3.7 NCAATourneyCompactResults

ncol: 8

knitr::kable(data[[7]] %>% head(10))

Season	DayNum	WTeamID	WScore	LTeamID	LScore	WLoc
1985	136	1116	63	1234	54	N
1985	136	1120	59	1345	58	N
1985	136	1207	68	1250	43	N
1985	136	1229	58	1425	55	N
1985	136	1242	49	1325	38	N
1985	136	1246	66	1449	58	N
1985	136	1256	78	1338	54	N
1985	136	1260	59	1233	58	N
1985	136	1314	76	1292	57	N
1985	136	1323	79	1333	70	N

3.8 NCAATourneyDetailedResults

ncol: 34

knitr::kable(data[[8]] %>% head(10))

Season	DayNum	WTeamID	WScore	LTeamID	LScore	WLoc	NumOT	WFGM	WFGA	WFGM3	WFGA3	WFTM	WFTA	WOR	WDR	WAst	WTO	WStl	WBlk	WPF	LFGM	LFGA	LFGM3	LFGA3	LFTM	LFTA	LOR	LDR	LAst	LTO	LStl	LBlk	LPF
2003	134	1421	92	1411	84	N	1	32	69	11	29	17	26	14	30	17	12	5	3	22	29	67	12	31	14	31	17	28	16	15	5	0	22
2003	136	1112	80	1436	51	N	0	31	66	7	23	11	14	11	36	22	16	10	7	8	20	64	4	16	7	7	8	26	12	17	10	3	15
2003	136	1113	84	1272	71	N	0	31	59	6	14	16	22	10	27	18	9	7	4	19	25	69	7	28	14	21	20	22	11	12	2	5	18
2003	136	1141	79	1166	73	N	0	29	53	3	7	18	25	11	20	15	18	13	1	19	27	60	7	17	12	17	14	17	20	21	6	6	21
2003	136	1143	76	1301	74	N	1	27	64	7	20	15	23	18	20	17	13	8	2	14	25	56	9	21	15	20	10	26	16	14	5	8	19
2003	136	1163	58	1140	53	N	0	17	52	4	14	20	27	12	29	8	14	3	8	16	20	64	2	17	11	13	15	26	11	11	8	4	22
2003	136	1181	67	1161	57	N	0	19	54	4	13	25	31	13	27	4	16	10	8	23	18	54	3	11	18	22	11	24	8	19	5	4	19
2003	136	1211	74	1153	69	N	0	20	47	6	14	28	37	8	28	12	12	2	2	15	26	66	10	27	7	10	13	22	13	10	7	6	24
2003	136	1228	65	1443	60	N	0	24	56	5	14	12	14	15	23	15	14	11	4	14	22	58	8	24	8	13	17	18	10	14	6	5	16
2003	136	1242	64	1429	61	N	0	28	51	2	6	6	11	7	20	13	11	8	4	17	23	56	6	17	9	10	13	19	13	13	6	1	15

3.9 NCAATourneySeedRoundSlots

ncol: 5

knitr::kable(data[[9]] %>% head(10))

Seed	GameRound	GameSlot	EarlyDayNum	LateDayNum
W01	1	R1W1	136	137
W01	2	R2W1	138	139
W01	3	R3W1	143	144
W01	4	R4W1	145	146
W01	5	R5WX	152	152
W01	6	R6CH	154	154
W02	1	R1W2	136	137
W02	2	R2W2	138	139
W02	3	R3W2	143	144
W02	4	R4W1	145	146

3.10 NCAATourneySeeds

ncol: 3

knitr::kable(data[[10]] %>% head(10))

Season	Seed	TeamID
1985	W01	1207
1985	W02	1210
1985	W03	1228
1985	W04	1260
1985	W05	1374
1985	W06	1208
1985	W07	1393
1985	W08	1396
1985	W09	1439
1985	W10	1177

3.11 NCAATourneySlots

ncol: 4

knitr::kable(data[[11]] %>% head(10))

Season	Slot	StrongSeed	WeakSeed
1985	R1W1	W01	W16
1985	R1W2	W02	W15
1985	R1W3	W03	W14
1985	R1W4	W04	W13
1985	R1W5	W05	W12
1985	R1W6	W06	W11
1985	R1W7	W07	W10
1985	R1W8	W08	W09
1985	R1X1	X01	X16
1985	R1X2	X02	X15

3.12 Players_2010

ncol: 4

knitr::kable(data[[12]] %>% head(10))

PlayerID	Season	TeamID	PlayerName
600001	2010	1102	BOHANNON_ZACH
600002	2010	1102	BRAKEVILLE_ADAM
600003	2010	1102	BROEKHUIS_TAYLOR
600004	2010	1102	BROOKS_DEREK
600005	2010	1102	EL-AMIN_SAJ
600006	2010	1102	FITZGERALD_MIKE
600007	2010	1102	FLETCHER_TODD
600008	2010	1102	FOW_TOM
600009	2010	1102	GREEN_KYLE
600010	2010	1102	HEMPSEY_SHAWN

3.13 RegularSeasonCompactResults

ncol: 8

knitr::kable(data[[13]] %>% head(10))

Season	DayNum	WTeamID	WScore	LTeamID	LScore	WLoc
1985	20	1228	81	1328	64	N
1985	25	1106	77	1354	70	H
1985	25	1112	63	1223	56	H
1985	25	1165	70	1432	54	H
1985	25	1192	86	1447	74	H
1985	25	1218	79	1337	78	H
1985	25	1228	64	1226	44	N
1985	25	1242	58	1268	56	N
1985	25	1260	98	1133	80	H
1985	25	1305	97	1424	89	H

3.14 RegularSeasonDetailedResults

ncol: 34

knitr::kable(data[[14]] %>% head(10))

Season	DayNum	WTeamID	WScore	LTeamID	LScore	WLoc	WFGM	WFGA	WFGM3	WFGA3	WFTM	WFTA	WOR	WDR	WAst	WTO	WStl	WBlk	WPF	LFGM	LFGA	LFGM3	LFGA3	LFTM	LFTA	LOR	LDR	LAst	LTO	LStl	LBlk	LPF
2003	10	1104	68	1328	62	N	27	58	3	14	11	18	14	24	13	23	7	1	22	22	53	2	10	16	22	10	22	8	18	9	2	20
2003	10	1272	70	1393	63	N	26	62	8	20	10	19	15	28	16	13	4	4	18	24	67	6	24	9	20	20	25	7	12	8	6	16
2003	11	1266	73	1437	61	N	24	58	8	18	17	29	17	26	15	10	5	2	25	22	73	3	26	14	23	31	22	9	12	2	5	23
2003	11	1296	56	1457	50	N	18	38	3	9	17	31	6	19	11	12	14	2	18	18	49	6	22	8	15	17	20	9	19	4	3	23
2003	11	1400	77	1208	71	N	30	61	6	14	11	13	17	22	12	14	4	4	20	24	62	6	16	17	27	21	15	12	10	7	1	14
2003	11	1458	81	1186	55	H	26	57	6	12	23	27	12	24	12	9	9	3	18	20	46	3	11	12	17	6	22	8	19	4	3	25
2003	12	1161	80	1236	62	H	23	55	2	8	32	39	13	18	14	17	11	1	25	19	41	4	15	20	28	9	21	11	30	10	4	28
2003	12	1186	75	1457	61	N	28	62	4	14	15	21	13	35	19	19	7	2	21	20	59	4	17	17	23	8	25	10	15	14	8	18
2003	12	1194	71	1156	66	N	28	58	5	11	10	18	9	22	9	17	9	2	23	24	52	6	18	12	27	13	26	13	25	8	2	18
2003	12	1458	84	1296	56	H	32	67	5	17	15	19	14	22	11	6	12	0	13	23	52	3	14	7	12	9	23	10	18	1	3	18

3.15 Seasons

ncol: 6

knitr::kable(data[[15]] %>% head(10))

Season	DayZero	RegionW	RegionX	RegionY	RegionZ
1985	10/29/1984	East	West	Midwest	Southeast
1986	10/28/1985	East	Midwest	Southeast	West
1987	10/27/1986	East	Southeast	Midwest	West
1988	11/2/1987	East	Midwest	Southeast	West
1989	10/31/1988	East	West	Midwest	Southeast
1990	10/30/1989	East	Midwest	Southeast	West
1991	10/29/1990	East	Southeast	Midwest	West
1992	11/4/1991	East	West	Midwest	Southeast
1993	11/2/1992	East	Midwest	Southeast	West
1994	11/1/1993	East	Southeast	Midwest	West

3.16 SecondaryTourneyCompactResults

ncol: 9

knitr::kable(data[[16]] %>% head(10))

Season	DayNum	WTeamID	WScore	LTeamID	LScore	WLoc	SecondaryTourney
1985	136	1151	67	1155	65	H	NIT
1985	136	1153	77	1245	61	H	NIT
1985	136	1201	79	1365	76	H	NIT
1985	136	1231	79	1139	57	H	NIT
1985	136	1249	78	1222	71	H	NIT
1985	136	1257	77	1108	75	H	NIT
1985	136	1266	77	1133	64	H	NIT
1985	136	1304	79	1145	66	H	NIT
1985	136	1307	80	1401	67	H	NIT
1985	136	1350	59	1200	57	H	NIT

3.17 SecondaryTourneyTeams

ncol: 3

knitr::kable(data[[17]] %>% head(10))

Season	SecondaryTourney	TeamID
1985	NIT	1108
1985	NIT	1133
1985	NIT	1139
1985	NIT	1145
1985	NIT	1151
1985	NIT	1153
1985	NIT	1155
1985	NIT	1196
1985	NIT	1200
1985	NIT	1201

3.18 TeamCoaches

ncol: 5

knitr::kable(data[[18]] %>% head(10))

Season	TeamID	LastDayNum	CoachName
1985	1102	154	reggie_minton
1985	1103	154	bob_huggins
1985	1104	154	wimp_sanderson
1985	1106	154	james_oliver
1985	1108	154	davey_whitney
1985	1109	154	freddie_goss
1985	1110	154	ed_tapscott
1985	1111	154	kevin_cantwell
1985	1112	154	lute_olson
1985	1113	154	bob_weinhauer

3.19 TeamConferences

ncol: 3

knitr::kable(data[[19]] %>% head(10))

Season	TeamID	ConfAbbrev
1985	1114	a_sun
1985	1147	a_sun
1985	1204	a_sun
1985	1209	a_sun
1985	1215	a_sun
1985	1223	a_sun
1985	1273	a_sun
1985	1359	a_sun
1985	1182	a_ten
1985	1203	a_ten

3.20 Teams

ncol: 4

knitr::kable(data[[20]] %>% head(10))

TeamID	TeamName	FirstD1Season	LastD1Season
1101	Abilene Chr	2014	2019
1102	Air Force	1985	2019
1103	Akron	1985	2019
1104	Alabama	1985	2019
1105	Alabama A&M	2000	2019
1106	Alabama St	1985	2019
1107	Albany NY	2000	2019
1108	Alcorn St	1985	2019
1109	Alliant Intl	1985	1991
1110	American Univ	1985	2019

3.21 TeamSpellings

ncol: 2

knitr::kable(data[[21]] %>% head(10))

TeamNameSpelling	TeamID
a&m-corpus chris	1394
a&m-corpus christi	1394
abilene chr	1101
abilene christian	1101
abilene-christian	1101
air force	1102
air-force	1102
akron	1103
alabama	1104
alabama a&m	1105

Datamodelr and Show Data

gingi99

2019-02-19 21:19:19

1 Preparations

1.1 Settings

1.2 Data Prep

1.3 Data Check

2 Schema Card with primary keys

3 Show Data

3.1 Cities

3.2 Conferences

3.3 ConferenceTourneyGames

3.4 Events_2010

3.5 GameCities

3.6 MasseyOrdinals

3.7 NCAATourneyCompactResults

3.8 NCAATourneyDetailedResults

3.9 NCAATourneySeedRoundSlots

3.10 NCAATourneySeeds

3.11 NCAATourneySlots

3.12 Players_2010

3.13 RegularSeasonCompactResults

3.14 RegularSeasonDetailedResults

3.15 Seasons

3.16 SecondaryTourneyCompactResults

3.17 SecondaryTourneyTeams

3.18 TeamCoaches

3.19 TeamConferences

3.20 Teams

3.21 TeamSpellings